Integrates multiple sequence-based feature descriptors to sufficiently explore distinct information embedded in cell-penetrating peptides (CPPs). CPPred-RF is a machine-learning-based predicator that employs a well-established feature selection technique to improve the feature representation and construct a two-layer prediction framework based on the random forest algorithm. CPPred-RF is competitive or better than the state-of-the-art predictors in terms of predicting CPPs and their uptake efficiency.
Forecasts cell-penetrating peptides (CPPs) and their uptake efficiency. MLCPP is a web application which proposes a two-layer prediction framework intending to assign peptides to CPP or non-CPP categories. Additionally, it considers data from its amino acid sequence, including information such as amino acid index (AAI) or composition-transition-distribution (CTD), to determine their efficiency. This program can be applied for large-scale CPP prediction.
Performs cell penetrating peptides (CPP) prediction. KELM-CPPpred is a kernel extreme learning machine (KELM) based prediction model for cell penetrating peptide. The software allows selection of one or several classification models based on various features vectors and their hybrid implementation to be cell penetrating. It can assist researchers in designing and predicting CPPs.
Predicts potential novel cell-penetrating peptides (CPPs). SkipCPP-Pred implements an adaptive k-skip feature representation algorithm that captures the correlation information of residues and build the prediction model based on the random forest (RF) classifier. The software indicates if the queried sequences provided by the user is cell-penetrating peptide or not, as well as the prediction confidence. SkipCPP-Pred was assessed by evaluation metrics and a validation method.
Identifies the cell-penetrating peptides (CPPs) based on the sequence information. C2Pred is a free web server and a sequence-based software. The analysis of variance was used to seek optimized dipeptide composition. The anticipated overall success rates are 83.6 per cent by using 5-fold cross-validation. This method can be used to discriminate cell-penetrating peptides from non-cell-penetrating peptides.
0 - 0 of 0
0 - 0 of 0